Bayesian analysis and model selection of garch models with additive jumps

Christian Haefke, Leopold Soegner

    Research output: Chapter in Book/Report/Conference proceedingChapter

    Abstract

    This article investigates parameter estimation and model selection of GARCH models with additive jumps. Continuous noise is driven by Student-t innovations. Since the likelihood is not available in closed form, Bayesian simulation methods are applied to estimate the model parameters and perform model selection. Simulations suggest that the parameters of the jump process are difficult to estimate. Informative priors based on sample moments and tests on jumps are necessary to obtain reliable parameter estimates. In an application using S&P 500returns we estimate a 3% jump intensity. In addition, our model allows us to infer the impact of a jump on future volatility. Our estimates show that the impact of jumps on the conditional volatility is large compared to the impact of continuous innovations.

    Original languageEnglish (US)
    Title of host publicationRecent Advances and Future Directions in Causality, Prediction, and Specification Analysis
    Subtitle of host publicationEssays in Honor of Halbert L. White Jr
    PublisherSpringer New York
    Pages179-208
    Number of pages30
    ISBN (Electronic)9781461416531
    ISBN (Print)9781461416524
    DOIs
    StatePublished - Jan 1 2013

    Fingerprint

    Bayesian analysis
    Jump
    Model selection
    GARCH model
    Bayesian model
    Innovation
    Simulation methods
    Jump process
    Conditional volatility
    Continuous innovation
    Simulation
    Parameter estimation

    Keywords

    • Additive Jumps
    • Bayes Factors
    • Garch
    • Model Selection

    ASJC Scopus subject areas

    • Economics, Econometrics and Finance(all)
    • Business, Management and Accounting(all)

    Cite this

    Haefke, C., & Soegner, L. (2013). Bayesian analysis and model selection of garch models with additive jumps. In Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis: Essays in Honor of Halbert L. White Jr (pp. 179-208). Springer New York. https://doi.org/10.1007/978-1-4614-1653-1_7

    Bayesian analysis and model selection of garch models with additive jumps. / Haefke, Christian; Soegner, Leopold.

    Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis: Essays in Honor of Halbert L. White Jr. Springer New York, 2013. p. 179-208.

    Research output: Chapter in Book/Report/Conference proceedingChapter

    Haefke, C & Soegner, L 2013, Bayesian analysis and model selection of garch models with additive jumps. in Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis: Essays in Honor of Halbert L. White Jr. Springer New York, pp. 179-208. https://doi.org/10.1007/978-1-4614-1653-1_7
    Haefke C, Soegner L. Bayesian analysis and model selection of garch models with additive jumps. In Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis: Essays in Honor of Halbert L. White Jr. Springer New York. 2013. p. 179-208 https://doi.org/10.1007/978-1-4614-1653-1_7
    Haefke, Christian ; Soegner, Leopold. / Bayesian analysis and model selection of garch models with additive jumps. Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis: Essays in Honor of Halbert L. White Jr. Springer New York, 2013. pp. 179-208
    @inbook{a5efdcafe1554ba0a98ce1401da4fa2c,
    title = "Bayesian analysis and model selection of garch models with additive jumps",
    abstract = "This article investigates parameter estimation and model selection of GARCH models with additive jumps. Continuous noise is driven by Student-t innovations. Since the likelihood is not available in closed form, Bayesian simulation methods are applied to estimate the model parameters and perform model selection. Simulations suggest that the parameters of the jump process are difficult to estimate. Informative priors based on sample moments and tests on jumps are necessary to obtain reliable parameter estimates. In an application using S&P 500returns we estimate a 3{\%} jump intensity. In addition, our model allows us to infer the impact of a jump on future volatility. Our estimates show that the impact of jumps on the conditional volatility is large compared to the impact of continuous innovations.",
    keywords = "Additive Jumps, Bayes Factors, Garch, Model Selection",
    author = "Christian Haefke and Leopold Soegner",
    year = "2013",
    month = "1",
    day = "1",
    doi = "10.1007/978-1-4614-1653-1_7",
    language = "English (US)",
    isbn = "9781461416524",
    pages = "179--208",
    booktitle = "Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis",
    publisher = "Springer New York",

    }

    TY - CHAP

    T1 - Bayesian analysis and model selection of garch models with additive jumps

    AU - Haefke, Christian

    AU - Soegner, Leopold

    PY - 2013/1/1

    Y1 - 2013/1/1

    N2 - This article investigates parameter estimation and model selection of GARCH models with additive jumps. Continuous noise is driven by Student-t innovations. Since the likelihood is not available in closed form, Bayesian simulation methods are applied to estimate the model parameters and perform model selection. Simulations suggest that the parameters of the jump process are difficult to estimate. Informative priors based on sample moments and tests on jumps are necessary to obtain reliable parameter estimates. In an application using S&P 500returns we estimate a 3% jump intensity. In addition, our model allows us to infer the impact of a jump on future volatility. Our estimates show that the impact of jumps on the conditional volatility is large compared to the impact of continuous innovations.

    AB - This article investigates parameter estimation and model selection of GARCH models with additive jumps. Continuous noise is driven by Student-t innovations. Since the likelihood is not available in closed form, Bayesian simulation methods are applied to estimate the model parameters and perform model selection. Simulations suggest that the parameters of the jump process are difficult to estimate. Informative priors based on sample moments and tests on jumps are necessary to obtain reliable parameter estimates. In an application using S&P 500returns we estimate a 3% jump intensity. In addition, our model allows us to infer the impact of a jump on future volatility. Our estimates show that the impact of jumps on the conditional volatility is large compared to the impact of continuous innovations.

    KW - Additive Jumps

    KW - Bayes Factors

    KW - Garch

    KW - Model Selection

    UR - http://www.scopus.com/inward/record.url?scp=84949008752&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84949008752&partnerID=8YFLogxK

    U2 - 10.1007/978-1-4614-1653-1_7

    DO - 10.1007/978-1-4614-1653-1_7

    M3 - Chapter

    SN - 9781461416524

    SP - 179

    EP - 208

    BT - Recent Advances and Future Directions in Causality, Prediction, and Specification Analysis

    PB - Springer New York

    ER -